Title :
Generalized PHD filters via a general chain rule
Author :
Clark, Daniel ; Mahler, Ronald
Author_Institution :
Dept. of Electr., Electron. & Comput. Eng., Heriot-Watt Univ., Edinburgh, UK
Abstract :
This paper introduces a general chain rule (GCR) for Gâteaux differentials/Gâteaux derivatives, and describes its consequences for multitarget detection and tracking. After describing the GCR and its specific form for functionals and functional derivatives, we use it to derive two new PHD filters: (1) a PHD filter for general models of target-generated measurements with general clutter processes; and (2) a multisensor version of this filter.
Keywords :
clutter; filtering theory; object detection; sensor fusion; target tracking; GCR; Gâteaux differentials-Gâteaux derivatives; clutter processes; general chain rule; generalized PHD filters; multisensor version; multitarget detection; multitarget tracking; target-generated measurements; Approximation methods; Clutter; Current measurement; Equations; Filtering theory; Mathematical model; Target tracking; Gâteaux derivative; PHD filter; chain rule; finite-set statistics; functional derivative; random sets;
Conference_Titel :
Information Fusion (FUSION), 2012 15th International Conference on
Conference_Location :
Singapore
Print_ISBN :
978-1-4673-0417-7
Electronic_ISBN :
978-0-9824438-4-2
